Deep Learning for Chest Radiographs

Chapter 4: End-to-end pre-trained CNN-based computer-aided classification system design for chest radiographs

Abstract

This chapter gives an exhaustive description of the experiments carried out for the design of end-to-end pre-trained CNN-based CAC systems for chest radiographs. It explains in detail the concept of transfer learning, pre-trained networks, series network, DAG network, and architectural description of the pre-trained CNN model AlexNet. GoogLeNet and ResNet18 were used for carrying the experiments. The code snippets of the different experiments aim at giving a better understanding to the programmatic implementation of designing these CAC systems.

Keywords

Series network; DAG network; AlexNet; ResNet18; GoogLeNet; Transfer ...